Initial upload of Korean Medical LLM by HARI
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- args.json +369 -0
- config.json +31 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model-00001-of-00031.safetensors +3 -0
- model-00002-of-00031.safetensors +3 -0
- model-00003-of-00031.safetensors +3 -0
- model-00004-of-00031.safetensors +3 -0
- model-00005-of-00031.safetensors +3 -0
- model-00006-of-00031.safetensors +3 -0
- model-00007-of-00031.safetensors +3 -0
- model-00008-of-00031.safetensors +3 -0
- model-00009-of-00031.safetensors +3 -0
- model-00010-of-00031.safetensors +3 -0
- model-00011-of-00031.safetensors +3 -0
- model-00012-of-00031.safetensors +3 -0
- model-00013-of-00031.safetensors +3 -0
- model-00014-of-00031.safetensors +3 -0
- model-00015-of-00031.safetensors +3 -0
- model-00016-of-00031.safetensors +3 -0
- model-00017-of-00031.safetensors +3 -0
- model-00018-of-00031.safetensors +3 -0
- model-00019-of-00031.safetensors +3 -0
- model-00020-of-00031.safetensors +3 -0
- model-00021-of-00031.safetensors +3 -0
- model-00022-of-00031.safetensors +3 -0
- model-00023-of-00031.safetensors +3 -0
- model-00024-of-00031.safetensors +3 -0
- model-00025-of-00031.safetensors +3 -0
- model-00026-of-00031.safetensors +3 -0
- model-00027-of-00031.safetensors +3 -0
- model-00028-of-00031.safetensors +3 -0
- model-00029-of-00031.safetensors +3 -0
- model-00030-of-00031.safetensors +3 -0
- model-00031-of-00031.safetensors +3 -0
- model.safetensors.index.json +970 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
args.json
ADDED
|
@@ -0,0 +1,369 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "/data1/hhoonlee_data/HARI/SNUH-HARI-72B-Instruct-Draft",
|
| 3 |
+
"model_type": "qwen2_5",
|
| 4 |
+
"model_revision": null,
|
| 5 |
+
"task_type": "causal_lm",
|
| 6 |
+
"torch_dtype": "bfloat16",
|
| 7 |
+
"attn_impl": "flash_attn",
|
| 8 |
+
"num_labels": null,
|
| 9 |
+
"problem_type": null,
|
| 10 |
+
"rope_scaling": null,
|
| 11 |
+
"device_map": null,
|
| 12 |
+
"max_memory": {},
|
| 13 |
+
"local_repo_path": null,
|
| 14 |
+
"template": "qwen",
|
| 15 |
+
"system": null,
|
| 16 |
+
"max_length": 32768,
|
| 17 |
+
"truncation_strategy": "delete",
|
| 18 |
+
"max_pixels": null,
|
| 19 |
+
"agent_template": null,
|
| 20 |
+
"norm_bbox": null,
|
| 21 |
+
"response_prefix": null,
|
| 22 |
+
"padding_side": "right",
|
| 23 |
+
"loss_scale": "default",
|
| 24 |
+
"sequence_parallel_size": 1,
|
| 25 |
+
"use_chat_template": true,
|
| 26 |
+
"template_backend": "swift",
|
| 27 |
+
"dataset": [
|
| 28 |
+
"/data1/hhoonlee_data/HARI/data/raw/sft_dataset_250326_sampled.json#40000"
|
| 29 |
+
],
|
| 30 |
+
"val_dataset": [],
|
| 31 |
+
"split_dataset_ratio": 0.01,
|
| 32 |
+
"data_seed": 42,
|
| 33 |
+
"dataset_num_proc": 1,
|
| 34 |
+
"dataset_shuffle": true,
|
| 35 |
+
"val_dataset_shuffle": false,
|
| 36 |
+
"streaming": false,
|
| 37 |
+
"interleave_prob": null,
|
| 38 |
+
"stopping_strategy": "first_exhausted",
|
| 39 |
+
"shuffle_buffer_size": 1000,
|
| 40 |
+
"enable_cache": false,
|
| 41 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 42 |
+
"columns": {},
|
| 43 |
+
"strict": false,
|
| 44 |
+
"remove_unused_columns": true,
|
| 45 |
+
"model_name": [
|
| 46 |
+
null,
|
| 47 |
+
null
|
| 48 |
+
],
|
| 49 |
+
"model_author": [
|
| 50 |
+
null,
|
| 51 |
+
null
|
| 52 |
+
],
|
| 53 |
+
"custom_dataset_info": [],
|
| 54 |
+
"quant_method": null,
|
| 55 |
+
"quant_bits": null,
|
| 56 |
+
"hqq_axis": null,
|
| 57 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 58 |
+
"bnb_4bit_quant_type": "nf4",
|
| 59 |
+
"bnb_4bit_use_double_quant": true,
|
| 60 |
+
"bnb_4bit_quant_storage": null,
|
| 61 |
+
"max_new_tokens": 8092,
|
| 62 |
+
"temperature": 0.0,
|
| 63 |
+
"top_k": null,
|
| 64 |
+
"top_p": null,
|
| 65 |
+
"repetition_penalty": null,
|
| 66 |
+
"num_beams": 1,
|
| 67 |
+
"stream": false,
|
| 68 |
+
"stop_words": [],
|
| 69 |
+
"logprobs": false,
|
| 70 |
+
"top_logprobs": null,
|
| 71 |
+
"ckpt_dir": null,
|
| 72 |
+
"load_dataset_config": null,
|
| 73 |
+
"lora_modules": [],
|
| 74 |
+
"tuner_backend": "peft",
|
| 75 |
+
"train_type": "lora",
|
| 76 |
+
"adapters": [],
|
| 77 |
+
"external_plugins": [],
|
| 78 |
+
"seed": 42,
|
| 79 |
+
"model_kwargs": {
|
| 80 |
+
"use_cache": false
|
| 81 |
+
},
|
| 82 |
+
"load_args": false,
|
| 83 |
+
"load_data_args": false,
|
| 84 |
+
"use_hf": true,
|
| 85 |
+
"hub_token": null,
|
| 86 |
+
"custom_register_path": [],
|
| 87 |
+
"ignore_args_error": false,
|
| 88 |
+
"use_swift_lora": false,
|
| 89 |
+
"output_dir": "/data1/hhoonlee_data/output_qwen25_72b_lora/v6-20250501-155817",
|
| 90 |
+
"overwrite_output_dir": false,
|
| 91 |
+
"do_train": false,
|
| 92 |
+
"do_eval": false,
|
| 93 |
+
"do_predict": false,
|
| 94 |
+
"eval_strategy": "steps",
|
| 95 |
+
"prediction_loss_only": false,
|
| 96 |
+
"per_device_train_batch_size": 1,
|
| 97 |
+
"per_device_eval_batch_size": 1,
|
| 98 |
+
"per_gpu_train_batch_size": null,
|
| 99 |
+
"per_gpu_eval_batch_size": null,
|
| 100 |
+
"gradient_accumulation_steps": 4,
|
| 101 |
+
"eval_accumulation_steps": null,
|
| 102 |
+
"eval_delay": 0,
|
| 103 |
+
"torch_empty_cache_steps": null,
|
| 104 |
+
"learning_rate": 0.0001,
|
| 105 |
+
"weight_decay": 0.1,
|
| 106 |
+
"adam_beta1": 0.9,
|
| 107 |
+
"adam_beta2": 0.95,
|
| 108 |
+
"adam_epsilon": 1e-08,
|
| 109 |
+
"max_grad_norm": 1.0,
|
| 110 |
+
"num_train_epochs": 1.0,
|
| 111 |
+
"max_steps": -1,
|
| 112 |
+
"lr_scheduler_type": "cosine",
|
| 113 |
+
"lr_scheduler_kwargs": null,
|
| 114 |
+
"warmup_ratio": 0.05,
|
| 115 |
+
"warmup_steps": 0,
|
| 116 |
+
"log_level": "passive",
|
| 117 |
+
"log_level_replica": "warning",
|
| 118 |
+
"log_on_each_node": true,
|
| 119 |
+
"logging_dir": "/data1/hhoonlee_data/output_qwen25_72b_lora/v6-20250501-155817/runs",
|
| 120 |
+
"logging_strategy": "steps",
|
| 121 |
+
"logging_first_step": true,
|
| 122 |
+
"logging_steps": 5,
|
| 123 |
+
"logging_nan_inf_filter": true,
|
| 124 |
+
"save_strategy": "steps",
|
| 125 |
+
"save_steps": 500.0,
|
| 126 |
+
"save_total_limit": 2,
|
| 127 |
+
"save_safetensors": true,
|
| 128 |
+
"save_on_each_node": false,
|
| 129 |
+
"save_only_model": false,
|
| 130 |
+
"restore_callback_states_from_checkpoint": false,
|
| 131 |
+
"no_cuda": false,
|
| 132 |
+
"use_cpu": false,
|
| 133 |
+
"use_mps_device": false,
|
| 134 |
+
"jit_mode_eval": false,
|
| 135 |
+
"use_ipex": false,
|
| 136 |
+
"bf16": true,
|
| 137 |
+
"fp16": false,
|
| 138 |
+
"fp16_opt_level": "O1",
|
| 139 |
+
"half_precision_backend": "auto",
|
| 140 |
+
"bf16_full_eval": false,
|
| 141 |
+
"fp16_full_eval": false,
|
| 142 |
+
"tf32": null,
|
| 143 |
+
"local_rank": 0,
|
| 144 |
+
"ddp_backend": null,
|
| 145 |
+
"tpu_num_cores": null,
|
| 146 |
+
"tpu_metrics_debug": false,
|
| 147 |
+
"debug": null,
|
| 148 |
+
"dataloader_drop_last": false,
|
| 149 |
+
"eval_steps": 500.0,
|
| 150 |
+
"dataloader_num_workers": 4,
|
| 151 |
+
"dataloader_prefetch_factor": null,
|
| 152 |
+
"past_index": -1,
|
| 153 |
+
"run_name": null,
|
| 154 |
+
"disable_tqdm": null,
|
| 155 |
+
"label_names": null,
|
| 156 |
+
"load_best_model_at_end": false,
|
| 157 |
+
"metric_for_best_model": "loss",
|
| 158 |
+
"greater_is_better": false,
|
| 159 |
+
"ignore_data_skip": false,
|
| 160 |
+
"fsdp": "",
|
| 161 |
+
"fsdp_min_num_params": 0,
|
| 162 |
+
"fsdp_config": null,
|
| 163 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 164 |
+
"accelerator_config": {
|
| 165 |
+
"dispatch_batches": false
|
| 166 |
+
},
|
| 167 |
+
"deepspeed": {
|
| 168 |
+
"fp16": {
|
| 169 |
+
"enabled": "auto",
|
| 170 |
+
"loss_scale": 0,
|
| 171 |
+
"loss_scale_window": 1000,
|
| 172 |
+
"initial_scale_power": 16,
|
| 173 |
+
"hysteresis": 2,
|
| 174 |
+
"min_loss_scale": 1
|
| 175 |
+
},
|
| 176 |
+
"bf16": {
|
| 177 |
+
"enabled": "auto"
|
| 178 |
+
},
|
| 179 |
+
"zero_optimization": {
|
| 180 |
+
"stage": 3,
|
| 181 |
+
"offload_optimizer": {
|
| 182 |
+
"device": "none",
|
| 183 |
+
"pin_memory": true
|
| 184 |
+
},
|
| 185 |
+
"offload_param": {
|
| 186 |
+
"device": "none",
|
| 187 |
+
"pin_memory": true
|
| 188 |
+
},
|
| 189 |
+
"overlap_comm": false,
|
| 190 |
+
"contiguous_gradients": true,
|
| 191 |
+
"sub_group_size": 1000000000.0,
|
| 192 |
+
"reduce_bucket_size": "auto",
|
| 193 |
+
"zero_quantized_weights": false,
|
| 194 |
+
"zero_quantized_gradients": false,
|
| 195 |
+
"stage3_prefetch_bucket_size": "auto",
|
| 196 |
+
"stage3_param_persistence_threshold": "auto",
|
| 197 |
+
"stage3_max_live_parameters": 1000000000.0,
|
| 198 |
+
"stage3_max_reuse_distance": 1000000000.0,
|
| 199 |
+
"stage3_gather_16bit_weights_on_model_save": true
|
| 200 |
+
},
|
| 201 |
+
"gradient_accumulation_steps": "auto",
|
| 202 |
+
"gradient_clipping": "auto",
|
| 203 |
+
"steps_per_print": 2000,
|
| 204 |
+
"train_batch_size": "auto",
|
| 205 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 206 |
+
"wall_clock_breakdown": false
|
| 207 |
+
},
|
| 208 |
+
"label_smoothing_factor": 0.0,
|
| 209 |
+
"optim": "adamw_torch_fused",
|
| 210 |
+
"optim_args": null,
|
| 211 |
+
"adafactor": false,
|
| 212 |
+
"group_by_length": false,
|
| 213 |
+
"length_column_name": "length",
|
| 214 |
+
"report_to": [
|
| 215 |
+
"tensorboard"
|
| 216 |
+
],
|
| 217 |
+
"ddp_find_unused_parameters": null,
|
| 218 |
+
"ddp_bucket_cap_mb": null,
|
| 219 |
+
"ddp_broadcast_buffers": null,
|
| 220 |
+
"dataloader_pin_memory": true,
|
| 221 |
+
"dataloader_persistent_workers": false,
|
| 222 |
+
"skip_memory_metrics": true,
|
| 223 |
+
"use_legacy_prediction_loop": false,
|
| 224 |
+
"push_to_hub": false,
|
| 225 |
+
"resume_from_checkpoint": null,
|
| 226 |
+
"hub_model_id": null,
|
| 227 |
+
"hub_strategy": "every_save",
|
| 228 |
+
"hub_private_repo": null,
|
| 229 |
+
"hub_always_push": false,
|
| 230 |
+
"gradient_checkpointing": true,
|
| 231 |
+
"gradient_checkpointing_kwargs": "{\"use_reentrant\": true}",
|
| 232 |
+
"include_inputs_for_metrics": false,
|
| 233 |
+
"include_for_metrics": [],
|
| 234 |
+
"eval_do_concat_batches": true,
|
| 235 |
+
"fp16_backend": "auto",
|
| 236 |
+
"evaluation_strategy": "steps",
|
| 237 |
+
"push_to_hub_model_id": null,
|
| 238 |
+
"push_to_hub_organization": null,
|
| 239 |
+
"push_to_hub_token": null,
|
| 240 |
+
"mp_parameters": "",
|
| 241 |
+
"auto_find_batch_size": false,
|
| 242 |
+
"full_determinism": false,
|
| 243 |
+
"torchdynamo": null,
|
| 244 |
+
"ray_scope": "last",
|
| 245 |
+
"ddp_timeout": 1800,
|
| 246 |
+
"torch_compile": false,
|
| 247 |
+
"torch_compile_backend": null,
|
| 248 |
+
"torch_compile_mode": null,
|
| 249 |
+
"dispatch_batches": null,
|
| 250 |
+
"split_batches": null,
|
| 251 |
+
"include_tokens_per_second": false,
|
| 252 |
+
"include_num_input_tokens_seen": false,
|
| 253 |
+
"neftune_noise_alpha": null,
|
| 254 |
+
"optim_target_modules": null,
|
| 255 |
+
"batch_eval_metrics": false,
|
| 256 |
+
"eval_on_start": false,
|
| 257 |
+
"use_liger_kernel": true,
|
| 258 |
+
"eval_use_gather_object": false,
|
| 259 |
+
"average_tokens_across_devices": false,
|
| 260 |
+
"sortish_sampler": false,
|
| 261 |
+
"predict_with_generate": false,
|
| 262 |
+
"generation_max_length": null,
|
| 263 |
+
"generation_num_beams": null,
|
| 264 |
+
"generation_config": null,
|
| 265 |
+
"check_model": true,
|
| 266 |
+
"acc_strategy": "token",
|
| 267 |
+
"train_dataloader_shuffle": true,
|
| 268 |
+
"metric_warmup_step": 0,
|
| 269 |
+
"fsdp_num": 1,
|
| 270 |
+
"acc_steps": 1,
|
| 271 |
+
"eval_use_evalscope": false,
|
| 272 |
+
"eval_datasets": [],
|
| 273 |
+
"eval_limit": null,
|
| 274 |
+
"eval_datasets_args": null,
|
| 275 |
+
"eval_generation_config": null,
|
| 276 |
+
"freeze_parameters": [],
|
| 277 |
+
"freeze_parameters_ratio": 0.0,
|
| 278 |
+
"trainable_parameters": [],
|
| 279 |
+
"freeze_llm": false,
|
| 280 |
+
"freeze_vit": true,
|
| 281 |
+
"freeze_aligner": true,
|
| 282 |
+
"target_modules": [
|
| 283 |
+
"all-linear"
|
| 284 |
+
],
|
| 285 |
+
"target_regex": null,
|
| 286 |
+
"modules_to_save": [],
|
| 287 |
+
"lora_rank": 16,
|
| 288 |
+
"lora_alpha": 32,
|
| 289 |
+
"lora_dropout": 0.05,
|
| 290 |
+
"lora_bias": "none",
|
| 291 |
+
"lora_dtype": null,
|
| 292 |
+
"lorap_lr_ratio": null,
|
| 293 |
+
"use_rslora": false,
|
| 294 |
+
"use_dora": false,
|
| 295 |
+
"lora_ga_batch_size": 2,
|
| 296 |
+
"lora_ga_iters": 2,
|
| 297 |
+
"lora_ga_max_length": 1024,
|
| 298 |
+
"lora_ga_direction": "ArB2r",
|
| 299 |
+
"lora_ga_scale": "stable",
|
| 300 |
+
"lora_ga_stable_gamma": 16,
|
| 301 |
+
"init_weights": true,
|
| 302 |
+
"fourier_n_frequency": 2000,
|
| 303 |
+
"fourier_scaling": 300.0,
|
| 304 |
+
"boft_block_size": 4,
|
| 305 |
+
"boft_block_num": 0,
|
| 306 |
+
"boft_n_butterfly_factor": 1,
|
| 307 |
+
"boft_dropout": 0.0,
|
| 308 |
+
"vera_rank": 256,
|
| 309 |
+
"vera_projection_prng_key": 0,
|
| 310 |
+
"vera_dropout": 0.0,
|
| 311 |
+
"vera_d_initial": 0.1,
|
| 312 |
+
"adapter_act": "gelu",
|
| 313 |
+
"adapter_length": 128,
|
| 314 |
+
"use_galore": false,
|
| 315 |
+
"galore_target_modules": null,
|
| 316 |
+
"galore_rank": 128,
|
| 317 |
+
"galore_update_proj_gap": 50,
|
| 318 |
+
"galore_scale": 1.0,
|
| 319 |
+
"galore_proj_type": "std",
|
| 320 |
+
"galore_optim_per_parameter": false,
|
| 321 |
+
"galore_with_embedding": false,
|
| 322 |
+
"galore_quantization": false,
|
| 323 |
+
"galore_proj_quant": false,
|
| 324 |
+
"galore_proj_bits": 4,
|
| 325 |
+
"galore_proj_group_size": 256,
|
| 326 |
+
"galore_cos_threshold": 0.4,
|
| 327 |
+
"galore_gamma_proj": 2,
|
| 328 |
+
"galore_queue_size": 5,
|
| 329 |
+
"adalora_target_r": 8,
|
| 330 |
+
"adalora_init_r": 12,
|
| 331 |
+
"adalora_tinit": 0,
|
| 332 |
+
"adalora_tfinal": 0,
|
| 333 |
+
"adalora_deltaT": 1,
|
| 334 |
+
"adalora_beta1": 0.85,
|
| 335 |
+
"adalora_beta2": 0.85,
|
| 336 |
+
"adalora_orth_reg_weight": 0.5,
|
| 337 |
+
"llamapro_num_new_blocks": 4,
|
| 338 |
+
"llamapro_num_groups": null,
|
| 339 |
+
"lisa_activated_layers": 0,
|
| 340 |
+
"lisa_step_interval": 20,
|
| 341 |
+
"reft_layer_key": null,
|
| 342 |
+
"reft_layers": null,
|
| 343 |
+
"reft_rank": 4,
|
| 344 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 345 |
+
"reft_args": null,
|
| 346 |
+
"swanlab_token": null,
|
| 347 |
+
"swanlab_project": null,
|
| 348 |
+
"swanlab_workspace": null,
|
| 349 |
+
"swanlab_exp_name": null,
|
| 350 |
+
"swanlab_mode": "cloud",
|
| 351 |
+
"add_version": true,
|
| 352 |
+
"resume_only_model": false,
|
| 353 |
+
"create_checkpoint_symlink": false,
|
| 354 |
+
"packing": false,
|
| 355 |
+
"lazy_tokenize": false,
|
| 356 |
+
"loss_type": null,
|
| 357 |
+
"optimizer": null,
|
| 358 |
+
"metric": null,
|
| 359 |
+
"zero_hpz_partition_size": null,
|
| 360 |
+
"rank": 0,
|
| 361 |
+
"global_world_size": 8,
|
| 362 |
+
"local_world_size": 8,
|
| 363 |
+
"model_suffix": "SNUH-HARI-72B-Instruct-Draft",
|
| 364 |
+
"model_info": "ModelInfo(model_type='qwen2_5', model_dir='/data1/hhoonlee_data/HARI/SNUH-HARI-72B-Instruct-Draft', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)",
|
| 365 |
+
"model_meta": "ModelMeta(model_type='qwen2_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct', hf_model_id='Qwen/Qwen2.5-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct', hf_model_id='Qwen/Qwen2.5-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct', hf_model_id='Qwen/Qwen2.5-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct', hf_model_id='Qwen/Qwen2.5-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct', hf_model_id='Qwen/Qwen2.5-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B', hf_model_id='Qwen/Qwen2.5-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B', hf_model_id='Qwen/Qwen2.5-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B', hf_model_id='Qwen/Qwen2.5-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B', hf_model_id='Qwen/Qwen2.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B', hf_model_id='Qwen/Qwen2.5-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B', hf_model_id='Qwen/Qwen2.5-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B', hf_model_id='Qwen/Qwen2.5-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B', hf_model_id='Qwen/Qwen2.5-Coder-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B', hf_model_id='Qwen/Qwen2.5-Coder-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B', hf_model_id='Qwen/Qwen2.5-Coder-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B', hf_model_id='Qwen/Qwen2.5-Coder-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B', hf_model_id='Qwen/Qwen2.5-Coder-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B', hf_model_id='Qwen/Qwen2.5-Coder-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['coding'])], template='qwen2_5', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f46a0e6fac0>, model_arch='llama', architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.37'], tags=[])",
|
| 366 |
+
"model_dir": "/data1/hhoonlee_data/HARI/SNUH-HARI-72B-Instruct-Draft",
|
| 367 |
+
"hub": "<class 'swift.hub.hub.HFHub'>",
|
| 368 |
+
"training_args": "Seq2SeqTrainingArguments(output_dir='/data1/hhoonlee_data/output_qwen25_72b_lora/v6-20250501-155817', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/data1/hhoonlee_data/output_qwen25_72b_lora/v6-20250501-155817/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=500, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=500, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/data1/hhoonlee_data/output_qwen25_72b_lora/v6-20250501-155817', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': True}, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy='steps', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=True, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='lora', optimizer=None, local_repo_path=None, galore_config=None)"
|
| 369 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "SNUH-HARI-72B-Instruct-Draft",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 8192,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 29568,
|
| 13 |
+
"max_position_embeddings": 131072,
|
| 14 |
+
"max_window_layers": 80,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 64,
|
| 17 |
+
"num_hidden_layers": 80,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"pad_token_id": 151643,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 1000000.0,
|
| 24 |
+
"sliding_window": 131072,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "bfloat16",
|
| 27 |
+
"transformers_version": "4.49.0",
|
| 28 |
+
"use_cache": false,
|
| 29 |
+
"use_sliding_window": false,
|
| 30 |
+
"vocab_size": 152064
|
| 31 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.49.0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64995361f5198751846be88e207d05eb71ca84174b81b766bea5b3539033f5cb
|
| 3 |
+
size 4548798728
|
model-00002-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:421ac462bb9ebee31cbc26dc887c753c0768b49c963e2407931d76c863873af2
|
| 3 |
+
size 4964101384
|
model-00003-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0315109d994c23f5f2c6442d24a5ee66b8357be2b64b17ef4edd62e50d13c9ba
|
| 3 |
+
size 4781637328
|
model-00004-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e42aef1ee5d95d1bbf41dae183d115124950136b86e6521df08439d55d57069
|
| 3 |
+
size 4781670320
|
model-00005-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36a04c3ae97088afaa5c4269757a4112e30086e6e7d0f90a1a868394bde7477f
|
| 3 |
+
size 4781670360
|
model-00006-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18f2d79fbbf18ea03bc6ef145ac1753be8484bbda8ae53cf4e985eb62379c176
|
| 3 |
+
size 4964101416
|
model-00007-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46f74d28844e297442f7f9396f4a6eaac326bc23141736779aba2239bd8a0e5a
|
| 3 |
+
size 4781637360
|
model-00008-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c97e514c7a09f69eca798af3e40d13826c5945b5836bcee867efa41dae142f4a
|
| 3 |
+
size 4781670360
|
model-00009-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3906d80322da1119f61656cf57eef7b50b68b4f4763f2b3e7484dbeaccdbbca9
|
| 3 |
+
size 4781670360
|
model-00010-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:955c9ae77582042e608f1651e5633d38117804924af078560727d05d851aad6b
|
| 3 |
+
size 4964101416
|
model-00011-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b08a43d89ed273006e00dc1cf66341a31dffb36601298c32761ff493d7a635b5
|
| 3 |
+
size 4781637360
|
model-00012-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e46fcbd985a93066c7b41a18f78d4b8090ca35fb2d6b62d7e0d77070262d825
|
| 3 |
+
size 4781670360
|
model-00013-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e0a3e834f93fae7cb320964d597c0d83b7f0f3cab54b8828dd598b8ea52e3a8
|
| 3 |
+
size 4781670360
|
model-00014-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c5652163d74b6514cc84a56dbed0ecb73eaa50657feff469fe65f3cdefa9394
|
| 3 |
+
size 4964101416
|
model-00015-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f979b3793e2e74bd5130238f803ddf6486d92a09e21f306a5f6ba0c3859038c6
|
| 3 |
+
size 4781637360
|
model-00016-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:040d13c34fb17e02fabc845b596f0f7ca83dec8fce2ca2e9299ed08605f9cb57
|
| 3 |
+
size 4781670360
|
model-00017-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:490478548b9768add7415fa8b228bdf2a36e829e2581b2d658240c18d1c47867
|
| 3 |
+
size 4781670360
|
model-00018-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55dcdeb461ed781ae0c05ccd4c911e92cc4131fa4722a367edc205ffe300311b
|
| 3 |
+
size 4964101416
|
model-00019-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65f4045d54f1975f6a0aae7e2988e07a2541dffafa1196b092bd0c8252b10c35
|
| 3 |
+
size 4781637360
|
model-00020-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e2f6cfd3ac8f3f987601c50f5ee1f903a9c267d2e04aa9e6b8b594d2f33d7e0
|
| 3 |
+
size 4781670360
|
model-00021-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3da08e9a5075d3f7dcf60f53a5f0e0064c76bc761882351558b97ab8977cdd65
|
| 3 |
+
size 4781670360
|
model-00022-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b84b14f8e4d5549ab2cb254801d523f3eb56f7ca63a153f8e83af36f6a85da2b
|
| 3 |
+
size 4964101416
|
model-00023-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:981b6671526ed10cba95d83645e12d62ee23d205a61061d9fd0ea39ca79b4a7d
|
| 3 |
+
size 4781637360
|
model-00024-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e30e7702e534e2759ffcc9ff487e7f6a38d0ac1f9e9e15bf5e40431f249801d
|
| 3 |
+
size 4781670360
|
model-00025-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcfb617b24409854792ae80ffbd78a07dc2b292a6b56c03ba0605c4b12eae6df
|
| 3 |
+
size 4781670360
|
model-00026-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b20b3557d8b746791f1541e9d268d75b0ab3dec7c01b881364199e4ce960b4c0
|
| 3 |
+
size 4964101416
|
model-00027-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a1652bf7db2c0cad5ea4ce5fef602ee4b79a173d4dbfc41d3eee294d17b040d
|
| 3 |
+
size 4781637360
|
model-00028-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20154870b42e1f08f698f3c3547fdaf2b917f86876fc1216fd644f928d03a1aa
|
| 3 |
+
size 4781670360
|
model-00029-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:190012b5464a1f14878608ed05a311b91fbead7098606682f22402c249e5a68f
|
| 3 |
+
size 4781670360
|
model-00030-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12dcfd3a3933a733364469ca895c8ff0f9b74b4cac3db2c10858bb0f76ab3abf
|
| 3 |
+
size 3208747032
|
model-00031-of-00031.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96be8a56e193a322b0384a09a5b272d71aa28d2304899f0bfc00dd06adf5c76e
|
| 3 |
+
size 2491416704
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,970 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 145412407296
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00031-of-00031.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00031.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00031.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00031.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00031.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00031.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00031.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00031.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00031.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00031.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00031.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00031.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00031.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00031.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00031.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00031.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00031.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00031.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00031.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00031.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00031.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00031.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00031.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00031.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00031.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00031.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00005-of-00031.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00005-of-00031.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00005-of-00031.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00005-of-00031.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00005-of-00031.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00005-of-00031.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00005-of-00031.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00005-of-00031.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00005-of-00031.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00005-of-00031.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00005-of-00031.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00005-of-00031.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00005-of-00031.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00005-of-00031.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00005-of-00031.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00005-of-00031.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00005-of-00031.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00005-of-00031.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00005-of-00031.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00005-of-00031.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00005-of-00031.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00005-of-00031.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00005-of-00031.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00031.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00006-of-00031.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00006-of-00031.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00006-of-00031.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00006-of-00031.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00006-of-00031.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00005-of-00031.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00005-of-00031.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00005-of-00031.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00005-of-00031.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00005-of-00031.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00005-of-00031.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00031.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00006-of-00031.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00006-of-00031.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00006-of-00031.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00006-of-00031.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00006-of-00031.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00006-of-00031.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00006-of-00031.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00006-of-00031.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00006-of-00031.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00006-of-00031.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00006-of-00031.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00006-of-00031.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00006-of-00031.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00006-of-00031.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00006-of-00031.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00006-of-00031.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00031.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00006-of-00031.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00006-of-00031.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00006-of-00031.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00006-of-00031.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00006-of-00031.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00006-of-00031.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00006-of-00031.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00007-of-00031.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00007-of-00031.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00007-of-00031.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00007-of-00031.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00007-of-00031.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00007-of-00031.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00007-of-00031.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00007-of-00031.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00007-of-00031.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00007-of-00031.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00007-of-00031.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00007-of-00031.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00007-of-00031.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00007-of-00031.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00007-of-00031.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00007-of-00031.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00007-of-00031.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00007-of-00031.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00007-of-00031.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00007-of-00031.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00007-of-00031.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00007-of-00031.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00007-of-00031.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00007-of-00031.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00008-of-00031.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00008-of-00031.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00007-of-00031.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00007-of-00031.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00008-of-00031.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00007-of-00031.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00007-of-00031.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00007-of-00031.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00007-of-00031.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00007-of-00031.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00007-of-00031.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00007-of-00031.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00008-of-00031.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00008-of-00031.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00008-of-00031.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00008-of-00031.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00008-of-00031.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00008-of-00031.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00008-of-00031.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00008-of-00031.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00008-of-00031.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00008-of-00031.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00008-of-00031.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00008-of-00031.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00008-of-00031.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00008-of-00031.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00008-of-00031.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00008-of-00031.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00008-of-00031.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00008-of-00031.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00008-of-00031.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00008-of-00031.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00008-of-00031.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00008-of-00031.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00008-of-00031.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00008-of-00031.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00002-of-00031.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00031.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00031.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00031.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00031.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00031.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00031.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00031.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00031.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00031.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00031.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00031.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00009-of-00031.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00009-of-00031.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00008-of-00031.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00009-of-00031.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00009-of-00031.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00008-of-00031.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00008-of-00031.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00008-of-00031.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00008-of-00031.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00008-of-00031.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00008-of-00031.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00008-of-00031.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00009-of-00031.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00009-of-00031.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00009-of-00031.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00009-of-00031.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00009-of-00031.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00009-of-00031.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00009-of-00031.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00009-of-00031.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00009-of-00031.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00009-of-00031.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00009-of-00031.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00009-of-00031.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00009-of-00031.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00009-of-00031.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00009-of-00031.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00009-of-00031.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00009-of-00031.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00009-of-00031.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00009-of-00031.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00009-of-00031.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00009-of-00031.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00009-of-00031.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00009-of-00031.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00009-of-00031.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00010-of-00031.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00010-of-00031.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00010-of-00031.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00010-of-00031.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00010-of-00031.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00009-of-00031.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00009-of-00031.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00009-of-00031.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00009-of-00031.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00009-of-00031.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00009-of-00031.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00009-of-00031.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00010-of-00031.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00010-of-00031.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00010-of-00031.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00010-of-00031.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00010-of-00031.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00010-of-00031.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00010-of-00031.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00010-of-00031.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00010-of-00031.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00010-of-00031.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00010-of-00031.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00010-of-00031.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00010-of-00031.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00010-of-00031.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00010-of-00031.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00010-of-00031.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00010-of-00031.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00010-of-00031.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00010-of-00031.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00010-of-00031.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00010-of-00031.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00010-of-00031.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00010-of-00031.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00010-of-00031.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00011-of-00031.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00011-of-00031.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00011-of-00031.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00011-of-00031.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00011-of-00031.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00011-of-00031.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00011-of-00031.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00011-of-00031.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00011-of-00031.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00011-of-00031.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00011-of-00031.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00011-of-00031.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00011-of-00031.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00011-of-00031.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00011-of-00031.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00011-of-00031.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00011-of-00031.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00011-of-00031.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00011-of-00031.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00011-of-00031.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00011-of-00031.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00011-of-00031.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00011-of-00031.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00011-of-00031.safetensors",
|
| 260 |
+
"model.layers.28.input_layernorm.weight": "model-00012-of-00031.safetensors",
|
| 261 |
+
"model.layers.28.mlp.down_proj.weight": "model-00012-of-00031.safetensors",
|
| 262 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00011-of-00031.safetensors",
|
| 263 |
+
"model.layers.28.mlp.up_proj.weight": "model-00011-of-00031.safetensors",
|
| 264 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00012-of-00031.safetensors",
|
| 265 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00011-of-00031.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00011-of-00031.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00011-of-00031.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00011-of-00031.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00011-of-00031.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00011-of-00031.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00011-of-00031.safetensors",
|
| 272 |
+
"model.layers.29.input_layernorm.weight": "model-00012-of-00031.safetensors",
|
| 273 |
+
"model.layers.29.mlp.down_proj.weight": "model-00012-of-00031.safetensors",
|
| 274 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00012-of-00031.safetensors",
|
| 275 |
+
"model.layers.29.mlp.up_proj.weight": "model-00012-of-00031.safetensors",
|
| 276 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00012-of-00031.safetensors",
|
| 277 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00012-of-00031.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00012-of-00031.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00012-of-00031.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00012-of-00031.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00012-of-00031.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00012-of-00031.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00012-of-00031.safetensors",
|
| 284 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00031.safetensors",
|
| 285 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00031.safetensors",
|
| 286 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00031.safetensors",
|
| 287 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00031.safetensors",
|
| 288 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00031.safetensors",
|
| 289 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00031.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00031.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00031.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00031.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00031.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00031.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00031.safetensors",
|
| 296 |
+
"model.layers.30.input_layernorm.weight": "model-00012-of-00031.safetensors",
|
| 297 |
+
"model.layers.30.mlp.down_proj.weight": "model-00012-of-00031.safetensors",
|
| 298 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00012-of-00031.safetensors",
|
| 299 |
+
"model.layers.30.mlp.up_proj.weight": "model-00012-of-00031.safetensors",
|
| 300 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00012-of-00031.safetensors",
|
| 301 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00012-of-00031.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00012-of-00031.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00012-of-00031.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00012-of-00031.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00012-of-00031.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00012-of-00031.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00012-of-00031.safetensors",
|
| 308 |
+
"model.layers.31.input_layernorm.weight": "model-00013-of-00031.safetensors",
|
| 309 |
+
"model.layers.31.mlp.down_proj.weight": "model-00013-of-00031.safetensors",
|
| 310 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00012-of-00031.safetensors",
|
| 311 |
+
"model.layers.31.mlp.up_proj.weight": "model-00013-of-00031.safetensors",
|
| 312 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00013-of-00031.safetensors",
|
| 313 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00012-of-00031.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00012-of-00031.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00012-of-00031.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00012-of-00031.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00012-of-00031.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00012-of-00031.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00012-of-00031.safetensors",
|
| 320 |
+
"model.layers.32.input_layernorm.weight": "model-00013-of-00031.safetensors",
|
| 321 |
+
"model.layers.32.mlp.down_proj.weight": "model-00013-of-00031.safetensors",
|
| 322 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00013-of-00031.safetensors",
|
| 323 |
+
"model.layers.32.mlp.up_proj.weight": "model-00013-of-00031.safetensors",
|
| 324 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00013-of-00031.safetensors",
|
| 325 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00013-of-00031.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00013-of-00031.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00013-of-00031.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00013-of-00031.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00013-of-00031.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00013-of-00031.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00013-of-00031.safetensors",
|
| 332 |
+
"model.layers.33.input_layernorm.weight": "model-00013-of-00031.safetensors",
|
| 333 |
+
"model.layers.33.mlp.down_proj.weight": "model-00013-of-00031.safetensors",
|
| 334 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00013-of-00031.safetensors",
|
| 335 |
+
"model.layers.33.mlp.up_proj.weight": "model-00013-of-00031.safetensors",
|
| 336 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00013-of-00031.safetensors",
|
| 337 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00013-of-00031.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00013-of-00031.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00013-of-00031.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00013-of-00031.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00013-of-00031.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00013-of-00031.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00013-of-00031.safetensors",
|
| 344 |
+
"model.layers.34.input_layernorm.weight": "model-00014-of-00031.safetensors",
|
| 345 |
+
"model.layers.34.mlp.down_proj.weight": "model-00014-of-00031.safetensors",
|
| 346 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00014-of-00031.safetensors",
|
| 347 |
+
"model.layers.34.mlp.up_proj.weight": "model-00014-of-00031.safetensors",
|
| 348 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00014-of-00031.safetensors",
|
| 349 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00013-of-00031.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00013-of-00031.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00013-of-00031.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00013-of-00031.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00013-of-00031.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00013-of-00031.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00013-of-00031.safetensors",
|
| 356 |
+
"model.layers.35.input_layernorm.weight": "model-00014-of-00031.safetensors",
|
| 357 |
+
"model.layers.35.mlp.down_proj.weight": "model-00014-of-00031.safetensors",
|
| 358 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00014-of-00031.safetensors",
|
| 359 |
+
"model.layers.35.mlp.up_proj.weight": "model-00014-of-00031.safetensors",
|
| 360 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00014-of-00031.safetensors",
|
| 361 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00014-of-00031.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00014-of-00031.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00014-of-00031.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00014-of-00031.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00014-of-00031.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00014-of-00031.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00014-of-00031.safetensors",
|
| 368 |
+
"model.layers.36.input_layernorm.weight": "model-00014-of-00031.safetensors",
|
| 369 |
+
"model.layers.36.mlp.down_proj.weight": "model-00014-of-00031.safetensors",
|
| 370 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00014-of-00031.safetensors",
|
| 371 |
+
"model.layers.36.mlp.up_proj.weight": "model-00014-of-00031.safetensors",
|
| 372 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00014-of-00031.safetensors",
|
| 373 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00014-of-00031.safetensors",
|
| 374 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00014-of-00031.safetensors",
|
| 375 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00014-of-00031.safetensors",
|
| 376 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00014-of-00031.safetensors",
|
| 377 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00014-of-00031.safetensors",
|
| 378 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00014-of-00031.safetensors",
|
| 379 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00014-of-00031.safetensors",
|
| 380 |
+
"model.layers.37.input_layernorm.weight": "model-00015-of-00031.safetensors",
|
| 381 |
+
"model.layers.37.mlp.down_proj.weight": "model-00015-of-00031.safetensors",
|
| 382 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00015-of-00031.safetensors",
|
| 383 |
+
"model.layers.37.mlp.up_proj.weight": "model-00015-of-00031.safetensors",
|
| 384 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00015-of-00031.safetensors",
|
| 385 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00015-of-00031.safetensors",
|
| 386 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00015-of-00031.safetensors",
|
| 387 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00015-of-00031.safetensors",
|
| 388 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00015-of-00031.safetensors",
|
| 389 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00015-of-00031.safetensors",
|
| 390 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00015-of-00031.safetensors",
|
| 391 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00015-of-00031.safetensors",
|
| 392 |
+
"model.layers.38.input_layernorm.weight": "model-00015-of-00031.safetensors",
|
| 393 |
+
"model.layers.38.mlp.down_proj.weight": "model-00015-of-00031.safetensors",
|
| 394 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00015-of-00031.safetensors",
|
| 395 |
+
"model.layers.38.mlp.up_proj.weight": "model-00015-of-00031.safetensors",
|
| 396 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00015-of-00031.safetensors",
|
| 397 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00015-of-00031.safetensors",
|
| 398 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00015-of-00031.safetensors",
|
| 399 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00015-of-00031.safetensors",
|
| 400 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00015-of-00031.safetensors",
|
| 401 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00015-of-00031.safetensors",
|
| 402 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00015-of-00031.safetensors",
|
| 403 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00015-of-00031.safetensors",
|
| 404 |
+
"model.layers.39.input_layernorm.weight": "model-00016-of-00031.safetensors",
|
| 405 |
+
"model.layers.39.mlp.down_proj.weight": "model-00016-of-00031.safetensors",
|
| 406 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00015-of-00031.safetensors",
|
| 407 |
+
"model.layers.39.mlp.up_proj.weight": "model-00015-of-00031.safetensors",
|
| 408 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00016-of-00031.safetensors",
|
| 409 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00015-of-00031.safetensors",
|
| 410 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00015-of-00031.safetensors",
|
| 411 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00015-of-00031.safetensors",
|
| 412 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00015-of-00031.safetensors",
|
| 413 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00015-of-00031.safetensors",
|
| 414 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00015-of-00031.safetensors",
|
| 415 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00015-of-00031.safetensors",
|
| 416 |
+
"model.layers.4.input_layernorm.weight": "model-00003-of-00031.safetensors",
|
| 417 |
+
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00031.safetensors",
|
| 418 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00031.safetensors",
|
| 419 |
+
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00031.safetensors",
|
| 420 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00031.safetensors",
|
| 421 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00003-of-00031.safetensors",
|
| 422 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00031.safetensors",
|
| 423 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00031.safetensors",
|
| 424 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00003-of-00031.safetensors",
|
| 425 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00031.safetensors",
|
| 426 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00003-of-00031.safetensors",
|
| 427 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00031.safetensors",
|
| 428 |
+
"model.layers.40.input_layernorm.weight": "model-00016-of-00031.safetensors",
|
| 429 |
+
"model.layers.40.mlp.down_proj.weight": "model-00016-of-00031.safetensors",
|
| 430 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00016-of-00031.safetensors",
|
| 431 |
+
"model.layers.40.mlp.up_proj.weight": "model-00016-of-00031.safetensors",
|
| 432 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00016-of-00031.safetensors",
|
| 433 |
+
"model.layers.40.self_attn.k_proj.bias": "model-00016-of-00031.safetensors",
|
| 434 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00016-of-00031.safetensors",
|
| 435 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00016-of-00031.safetensors",
|
| 436 |
+
"model.layers.40.self_attn.q_proj.bias": "model-00016-of-00031.safetensors",
|
| 437 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00016-of-00031.safetensors",
|
| 438 |
+
"model.layers.40.self_attn.v_proj.bias": "model-00016-of-00031.safetensors",
|
| 439 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00016-of-00031.safetensors",
|
| 440 |
+
"model.layers.41.input_layernorm.weight": "model-00016-of-00031.safetensors",
|
| 441 |
+
"model.layers.41.mlp.down_proj.weight": "model-00016-of-00031.safetensors",
|
| 442 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00016-of-00031.safetensors",
|
| 443 |
+
"model.layers.41.mlp.up_proj.weight": "model-00016-of-00031.safetensors",
|
| 444 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00016-of-00031.safetensors",
|
| 445 |
+
"model.layers.41.self_attn.k_proj.bias": "model-00016-of-00031.safetensors",
|
| 446 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00016-of-00031.safetensors",
|
| 447 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00016-of-00031.safetensors",
|
| 448 |
+
"model.layers.41.self_attn.q_proj.bias": "model-00016-of-00031.safetensors",
|
| 449 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00016-of-00031.safetensors",
|
| 450 |
+
"model.layers.41.self_attn.v_proj.bias": "model-00016-of-00031.safetensors",
|
| 451 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00016-of-00031.safetensors",
|
| 452 |
+
"model.layers.42.input_layernorm.weight": "model-00017-of-00031.safetensors",
|
| 453 |
+
"model.layers.42.mlp.down_proj.weight": "model-00017-of-00031.safetensors",
|
| 454 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00016-of-00031.safetensors",
|
| 455 |
+
"model.layers.42.mlp.up_proj.weight": "model-00017-of-00031.safetensors",
|
| 456 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00017-of-00031.safetensors",
|
| 457 |
+
"model.layers.42.self_attn.k_proj.bias": "model-00016-of-00031.safetensors",
|
| 458 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00016-of-00031.safetensors",
|
| 459 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00016-of-00031.safetensors",
|
| 460 |
+
"model.layers.42.self_attn.q_proj.bias": "model-00016-of-00031.safetensors",
|
| 461 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00016-of-00031.safetensors",
|
| 462 |
+
"model.layers.42.self_attn.v_proj.bias": "model-00016-of-00031.safetensors",
|
| 463 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00016-of-00031.safetensors",
|
| 464 |
+
"model.layers.43.input_layernorm.weight": "model-00017-of-00031.safetensors",
|
| 465 |
+
"model.layers.43.mlp.down_proj.weight": "model-00017-of-00031.safetensors",
|
| 466 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00017-of-00031.safetensors",
|
| 467 |
+
"model.layers.43.mlp.up_proj.weight": "model-00017-of-00031.safetensors",
|
| 468 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00017-of-00031.safetensors",
|
| 469 |
+
"model.layers.43.self_attn.k_proj.bias": "model-00017-of-00031.safetensors",
|
| 470 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00017-of-00031.safetensors",
|
| 471 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00017-of-00031.safetensors",
|
| 472 |
+
"model.layers.43.self_attn.q_proj.bias": "model-00017-of-00031.safetensors",
|
| 473 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00017-of-00031.safetensors",
|
| 474 |
+
"model.layers.43.self_attn.v_proj.bias": "model-00017-of-00031.safetensors",
|
| 475 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00017-of-00031.safetensors",
|
| 476 |
+
"model.layers.44.input_layernorm.weight": "model-00017-of-00031.safetensors",
|
| 477 |
+
"model.layers.44.mlp.down_proj.weight": "model-00017-of-00031.safetensors",
|
| 478 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00017-of-00031.safetensors",
|
| 479 |
+
"model.layers.44.mlp.up_proj.weight": "model-00017-of-00031.safetensors",
|
| 480 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00017-of-00031.safetensors",
|
| 481 |
+
"model.layers.44.self_attn.k_proj.bias": "model-00017-of-00031.safetensors",
|
| 482 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00017-of-00031.safetensors",
|
| 483 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00017-of-00031.safetensors",
|
| 484 |
+
"model.layers.44.self_attn.q_proj.bias": "model-00017-of-00031.safetensors",
|
| 485 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00017-of-00031.safetensors",
|
| 486 |
+
"model.layers.44.self_attn.v_proj.bias": "model-00017-of-00031.safetensors",
|
| 487 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00017-of-00031.safetensors",
|
| 488 |
+
"model.layers.45.input_layernorm.weight": "model-00018-of-00031.safetensors",
|
| 489 |
+
"model.layers.45.mlp.down_proj.weight": "model-00018-of-00031.safetensors",
|
| 490 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00018-of-00031.safetensors",
|
| 491 |
+
"model.layers.45.mlp.up_proj.weight": "model-00018-of-00031.safetensors",
|
| 492 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00018-of-00031.safetensors",
|
| 493 |
+
"model.layers.45.self_attn.k_proj.bias": "model-00017-of-00031.safetensors",
|
| 494 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00017-of-00031.safetensors",
|
| 495 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00017-of-00031.safetensors",
|
| 496 |
+
"model.layers.45.self_attn.q_proj.bias": "model-00017-of-00031.safetensors",
|
| 497 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00017-of-00031.safetensors",
|
| 498 |
+
"model.layers.45.self_attn.v_proj.bias": "model-00017-of-00031.safetensors",
|
| 499 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00017-of-00031.safetensors",
|
| 500 |
+
"model.layers.46.input_layernorm.weight": "model-00018-of-00031.safetensors",
|
| 501 |
+
"model.layers.46.mlp.down_proj.weight": "model-00018-of-00031.safetensors",
|
| 502 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00018-of-00031.safetensors",
|
| 503 |
+
"model.layers.46.mlp.up_proj.weight": "model-00018-of-00031.safetensors",
|
| 504 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00018-of-00031.safetensors",
|
| 505 |
+
"model.layers.46.self_attn.k_proj.bias": "model-00018-of-00031.safetensors",
|
| 506 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00018-of-00031.safetensors",
|
| 507 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00018-of-00031.safetensors",
|
| 508 |
+
"model.layers.46.self_attn.q_proj.bias": "model-00018-of-00031.safetensors",
|
| 509 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00018-of-00031.safetensors",
|
| 510 |
+
"model.layers.46.self_attn.v_proj.bias": "model-00018-of-00031.safetensors",
|
| 511 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00018-of-00031.safetensors",
|
| 512 |
+
"model.layers.47.input_layernorm.weight": "model-00018-of-00031.safetensors",
|
| 513 |
+
"model.layers.47.mlp.down_proj.weight": "model-00018-of-00031.safetensors",
|
| 514 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00018-of-00031.safetensors",
|
| 515 |
+
"model.layers.47.mlp.up_proj.weight": "model-00018-of-00031.safetensors",
|
| 516 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00018-of-00031.safetensors",
|
| 517 |
+
"model.layers.47.self_attn.k_proj.bias": "model-00018-of-00031.safetensors",
|
| 518 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00018-of-00031.safetensors",
|
| 519 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00018-of-00031.safetensors",
|
| 520 |
+
"model.layers.47.self_attn.q_proj.bias": "model-00018-of-00031.safetensors",
|
| 521 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00018-of-00031.safetensors",
|
| 522 |
+
"model.layers.47.self_attn.v_proj.bias": "model-00018-of-00031.safetensors",
|
| 523 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00018-of-00031.safetensors",
|
| 524 |
+
"model.layers.48.input_layernorm.weight": "model-00019-of-00031.safetensors",
|
| 525 |
+
"model.layers.48.mlp.down_proj.weight": "model-00019-of-00031.safetensors",
|
| 526 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00019-of-00031.safetensors",
|
| 527 |
+
"model.layers.48.mlp.up_proj.weight": "model-00019-of-00031.safetensors",
|
| 528 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00019-of-00031.safetensors",
|
| 529 |
+
"model.layers.48.self_attn.k_proj.bias": "model-00019-of-00031.safetensors",
|
| 530 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00019-of-00031.safetensors",
|
| 531 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00019-of-00031.safetensors",
|
| 532 |
+
"model.layers.48.self_attn.q_proj.bias": "model-00019-of-00031.safetensors",
|
| 533 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00019-of-00031.safetensors",
|
| 534 |
+
"model.layers.48.self_attn.v_proj.bias": "model-00019-of-00031.safetensors",
|
| 535 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00019-of-00031.safetensors",
|
| 536 |
+
"model.layers.49.input_layernorm.weight": "model-00019-of-00031.safetensors",
|
| 537 |
+
"model.layers.49.mlp.down_proj.weight": "model-00019-of-00031.safetensors",
|
| 538 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00019-of-00031.safetensors",
|
| 539 |
+
"model.layers.49.mlp.up_proj.weight": "model-00019-of-00031.safetensors",
|
| 540 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00019-of-00031.safetensors",
|
| 541 |
+
"model.layers.49.self_attn.k_proj.bias": "model-00019-of-00031.safetensors",
|
| 542 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00019-of-00031.safetensors",
|
| 543 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00019-of-00031.safetensors",
|
| 544 |
+
"model.layers.49.self_attn.q_proj.bias": "model-00019-of-00031.safetensors",
|
| 545 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00019-of-00031.safetensors",
|
| 546 |
+
"model.layers.49.self_attn.v_proj.bias": "model-00019-of-00031.safetensors",
|
| 547 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00019-of-00031.safetensors",
|
| 548 |
+
"model.layers.5.input_layernorm.weight": "model-00003-of-00031.safetensors",
|
| 549 |
+
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00031.safetensors",
|
| 550 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00031.safetensors",
|
| 551 |
+
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00031.safetensors",
|
| 552 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00031.safetensors",
|
| 553 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00003-of-00031.safetensors",
|
| 554 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00031.safetensors",
|
| 555 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00031.safetensors",
|
| 556 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00003-of-00031.safetensors",
|
| 557 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00031.safetensors",
|
| 558 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00003-of-00031.safetensors",
|
| 559 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00031.safetensors",
|
| 560 |
+
"model.layers.50.input_layernorm.weight": "model-00020-of-00031.safetensors",
|
| 561 |
+
"model.layers.50.mlp.down_proj.weight": "model-00020-of-00031.safetensors",
|
| 562 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00019-of-00031.safetensors",
|
| 563 |
+
"model.layers.50.mlp.up_proj.weight": "model-00019-of-00031.safetensors",
|
| 564 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00020-of-00031.safetensors",
|
| 565 |
+
"model.layers.50.self_attn.k_proj.bias": "model-00019-of-00031.safetensors",
|
| 566 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00019-of-00031.safetensors",
|
| 567 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00019-of-00031.safetensors",
|
| 568 |
+
"model.layers.50.self_attn.q_proj.bias": "model-00019-of-00031.safetensors",
|
| 569 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00019-of-00031.safetensors",
|
| 570 |
+
"model.layers.50.self_attn.v_proj.bias": "model-00019-of-00031.safetensors",
|
| 571 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00019-of-00031.safetensors",
|
| 572 |
+
"model.layers.51.input_layernorm.weight": "model-00020-of-00031.safetensors",
|
| 573 |
+
"model.layers.51.mlp.down_proj.weight": "model-00020-of-00031.safetensors",
|
| 574 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00020-of-00031.safetensors",
|
| 575 |
+
"model.layers.51.mlp.up_proj.weight": "model-00020-of-00031.safetensors",
|
| 576 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00020-of-00031.safetensors",
|
| 577 |
+
"model.layers.51.self_attn.k_proj.bias": "model-00020-of-00031.safetensors",
|
| 578 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00020-of-00031.safetensors",
|
| 579 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00020-of-00031.safetensors",
|
| 580 |
+
"model.layers.51.self_attn.q_proj.bias": "model-00020-of-00031.safetensors",
|
| 581 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00020-of-00031.safetensors",
|
| 582 |
+
"model.layers.51.self_attn.v_proj.bias": "model-00020-of-00031.safetensors",
|
| 583 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00020-of-00031.safetensors",
|
| 584 |
+
"model.layers.52.input_layernorm.weight": "model-00020-of-00031.safetensors",
|
| 585 |
+
"model.layers.52.mlp.down_proj.weight": "model-00020-of-00031.safetensors",
|
| 586 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00020-of-00031.safetensors",
|
| 587 |
+
"model.layers.52.mlp.up_proj.weight": "model-00020-of-00031.safetensors",
|
| 588 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00020-of-00031.safetensors",
|
| 589 |
+
"model.layers.52.self_attn.k_proj.bias": "model-00020-of-00031.safetensors",
|
| 590 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00020-of-00031.safetensors",
|
| 591 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00020-of-00031.safetensors",
|
| 592 |
+
"model.layers.52.self_attn.q_proj.bias": "model-00020-of-00031.safetensors",
|
| 593 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00020-of-00031.safetensors",
|
| 594 |
+
"model.layers.52.self_attn.v_proj.bias": "model-00020-of-00031.safetensors",
|
| 595 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00020-of-00031.safetensors",
|
| 596 |
+
"model.layers.53.input_layernorm.weight": "model-00021-of-00031.safetensors",
|
| 597 |
+
"model.layers.53.mlp.down_proj.weight": "model-00021-of-00031.safetensors",
|
| 598 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00020-of-00031.safetensors",
|
| 599 |
+
"model.layers.53.mlp.up_proj.weight": "model-00021-of-00031.safetensors",
|
| 600 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00021-of-00031.safetensors",
|
| 601 |
+
"model.layers.53.self_attn.k_proj.bias": "model-00020-of-00031.safetensors",
|
| 602 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00020-of-00031.safetensors",
|
| 603 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00020-of-00031.safetensors",
|
| 604 |
+
"model.layers.53.self_attn.q_proj.bias": "model-00020-of-00031.safetensors",
|
| 605 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00020-of-00031.safetensors",
|
| 606 |
+
"model.layers.53.self_attn.v_proj.bias": "model-00020-of-00031.safetensors",
|
| 607 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00020-of-00031.safetensors",
|
| 608 |
+
"model.layers.54.input_layernorm.weight": "model-00021-of-00031.safetensors",
|
| 609 |
+
"model.layers.54.mlp.down_proj.weight": "model-00021-of-00031.safetensors",
|
| 610 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00021-of-00031.safetensors",
|
| 611 |
+
"model.layers.54.mlp.up_proj.weight": "model-00021-of-00031.safetensors",
|
| 612 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00021-of-00031.safetensors",
|
| 613 |
+
"model.layers.54.self_attn.k_proj.bias": "model-00021-of-00031.safetensors",
|
| 614 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00021-of-00031.safetensors",
|
| 615 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00021-of-00031.safetensors",
|
| 616 |
+
"model.layers.54.self_attn.q_proj.bias": "model-00021-of-00031.safetensors",
|
| 617 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00021-of-00031.safetensors",
|
| 618 |
+
"model.layers.54.self_attn.v_proj.bias": "model-00021-of-00031.safetensors",
|
| 619 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00021-of-00031.safetensors",
|
| 620 |
+
"model.layers.55.input_layernorm.weight": "model-00021-of-00031.safetensors",
|
| 621 |
+
"model.layers.55.mlp.down_proj.weight": "model-00021-of-00031.safetensors",
|
| 622 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00021-of-00031.safetensors",
|
| 623 |
+
"model.layers.55.mlp.up_proj.weight": "model-00021-of-00031.safetensors",
|
| 624 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00021-of-00031.safetensors",
|
| 625 |
+
"model.layers.55.self_attn.k_proj.bias": "model-00021-of-00031.safetensors",
|
| 626 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00021-of-00031.safetensors",
|
| 627 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00021-of-00031.safetensors",
|
| 628 |
+
"model.layers.55.self_attn.q_proj.bias": "model-00021-of-00031.safetensors",
|
| 629 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00021-of-00031.safetensors",
|
| 630 |
+
"model.layers.55.self_attn.v_proj.bias": "model-00021-of-00031.safetensors",
|
| 631 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00021-of-00031.safetensors",
|
| 632 |
+
"model.layers.56.input_layernorm.weight": "model-00022-of-00031.safetensors",
|
| 633 |
+
"model.layers.56.mlp.down_proj.weight": "model-00022-of-00031.safetensors",
|
| 634 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00022-of-00031.safetensors",
|
| 635 |
+
"model.layers.56.mlp.up_proj.weight": "model-00022-of-00031.safetensors",
|
| 636 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00022-of-00031.safetensors",
|
| 637 |
+
"model.layers.56.self_attn.k_proj.bias": "model-00021-of-00031.safetensors",
|
| 638 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00021-of-00031.safetensors",
|
| 639 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00021-of-00031.safetensors",
|
| 640 |
+
"model.layers.56.self_attn.q_proj.bias": "model-00021-of-00031.safetensors",
|
| 641 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00021-of-00031.safetensors",
|
| 642 |
+
"model.layers.56.self_attn.v_proj.bias": "model-00021-of-00031.safetensors",
|
| 643 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00021-of-00031.safetensors",
|
| 644 |
+
"model.layers.57.input_layernorm.weight": "model-00022-of-00031.safetensors",
|
| 645 |
+
"model.layers.57.mlp.down_proj.weight": "model-00022-of-00031.safetensors",
|
| 646 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00022-of-00031.safetensors",
|
| 647 |
+
"model.layers.57.mlp.up_proj.weight": "model-00022-of-00031.safetensors",
|
| 648 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00022-of-00031.safetensors",
|
| 649 |
+
"model.layers.57.self_attn.k_proj.bias": "model-00022-of-00031.safetensors",
|
| 650 |
+
"model.layers.57.self_attn.k_proj.weight": "model-00022-of-00031.safetensors",
|
| 651 |
+
"model.layers.57.self_attn.o_proj.weight": "model-00022-of-00031.safetensors",
|
| 652 |
+
"model.layers.57.self_attn.q_proj.bias": "model-00022-of-00031.safetensors",
|
| 653 |
+
"model.layers.57.self_attn.q_proj.weight": "model-00022-of-00031.safetensors",
|
| 654 |
+
"model.layers.57.self_attn.v_proj.bias": "model-00022-of-00031.safetensors",
|
| 655 |
+
"model.layers.57.self_attn.v_proj.weight": "model-00022-of-00031.safetensors",
|
| 656 |
+
"model.layers.58.input_layernorm.weight": "model-00022-of-00031.safetensors",
|
| 657 |
+
"model.layers.58.mlp.down_proj.weight": "model-00022-of-00031.safetensors",
|
| 658 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00022-of-00031.safetensors",
|
| 659 |
+
"model.layers.58.mlp.up_proj.weight": "model-00022-of-00031.safetensors",
|
| 660 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00022-of-00031.safetensors",
|
| 661 |
+
"model.layers.58.self_attn.k_proj.bias": "model-00022-of-00031.safetensors",
|
| 662 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00022-of-00031.safetensors",
|
| 663 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00022-of-00031.safetensors",
|
| 664 |
+
"model.layers.58.self_attn.q_proj.bias": "model-00022-of-00031.safetensors",
|
| 665 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00022-of-00031.safetensors",
|
| 666 |
+
"model.layers.58.self_attn.v_proj.bias": "model-00022-of-00031.safetensors",
|
| 667 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00022-of-00031.safetensors",
|
| 668 |
+
"model.layers.59.input_layernorm.weight": "model-00023-of-00031.safetensors",
|
| 669 |
+
"model.layers.59.mlp.down_proj.weight": "model-00023-of-00031.safetensors",
|
| 670 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00023-of-00031.safetensors",
|
| 671 |
+
"model.layers.59.mlp.up_proj.weight": "model-00023-of-00031.safetensors",
|
| 672 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00023-of-00031.safetensors",
|
| 673 |
+
"model.layers.59.self_attn.k_proj.bias": "model-00023-of-00031.safetensors",
|
| 674 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00023-of-00031.safetensors",
|
| 675 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00023-of-00031.safetensors",
|
| 676 |
+
"model.layers.59.self_attn.q_proj.bias": "model-00023-of-00031.safetensors",
|
| 677 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00023-of-00031.safetensors",
|
| 678 |
+
"model.layers.59.self_attn.v_proj.bias": "model-00023-of-00031.safetensors",
|
| 679 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00023-of-00031.safetensors",
|
| 680 |
+
"model.layers.6.input_layernorm.weight": "model-00004-of-00031.safetensors",
|
| 681 |
+
"model.layers.6.mlp.down_proj.weight": "model-00004-of-00031.safetensors",
|
| 682 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00031.safetensors",
|
| 683 |
+
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00031.safetensors",
|
| 684 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00004-of-00031.safetensors",
|
| 685 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00003-of-00031.safetensors",
|
| 686 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00031.safetensors",
|
| 687 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00031.safetensors",
|
| 688 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00003-of-00031.safetensors",
|
| 689 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00031.safetensors",
|
| 690 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00031.safetensors",
|
| 691 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00031.safetensors",
|
| 692 |
+
"model.layers.60.input_layernorm.weight": "model-00023-of-00031.safetensors",
|
| 693 |
+
"model.layers.60.mlp.down_proj.weight": "model-00023-of-00031.safetensors",
|
| 694 |
+
"model.layers.60.mlp.gate_proj.weight": "model-00023-of-00031.safetensors",
|
| 695 |
+
"model.layers.60.mlp.up_proj.weight": "model-00023-of-00031.safetensors",
|
| 696 |
+
"model.layers.60.post_attention_layernorm.weight": "model-00023-of-00031.safetensors",
|
| 697 |
+
"model.layers.60.self_attn.k_proj.bias": "model-00023-of-00031.safetensors",
|
| 698 |
+
"model.layers.60.self_attn.k_proj.weight": "model-00023-of-00031.safetensors",
|
| 699 |
+
"model.layers.60.self_attn.o_proj.weight": "model-00023-of-00031.safetensors",
|
| 700 |
+
"model.layers.60.self_attn.q_proj.bias": "model-00023-of-00031.safetensors",
|
| 701 |
+
"model.layers.60.self_attn.q_proj.weight": "model-00023-of-00031.safetensors",
|
| 702 |
+
"model.layers.60.self_attn.v_proj.bias": "model-00023-of-00031.safetensors",
|
| 703 |
+
"model.layers.60.self_attn.v_proj.weight": "model-00023-of-00031.safetensors",
|
| 704 |
+
"model.layers.61.input_layernorm.weight": "model-00024-of-00031.safetensors",
|
| 705 |
+
"model.layers.61.mlp.down_proj.weight": "model-00024-of-00031.safetensors",
|
| 706 |
+
"model.layers.61.mlp.gate_proj.weight": "model-00023-of-00031.safetensors",
|
| 707 |
+
"model.layers.61.mlp.up_proj.weight": "model-00023-of-00031.safetensors",
|
| 708 |
+
"model.layers.61.post_attention_layernorm.weight": "model-00024-of-00031.safetensors",
|
| 709 |
+
"model.layers.61.self_attn.k_proj.bias": "model-00023-of-00031.safetensors",
|
| 710 |
+
"model.layers.61.self_attn.k_proj.weight": "model-00023-of-00031.safetensors",
|
| 711 |
+
"model.layers.61.self_attn.o_proj.weight": "model-00023-of-00031.safetensors",
|
| 712 |
+
"model.layers.61.self_attn.q_proj.bias": "model-00023-of-00031.safetensors",
|
| 713 |
+
"model.layers.61.self_attn.q_proj.weight": "model-00023-of-00031.safetensors",
|
| 714 |
+
"model.layers.61.self_attn.v_proj.bias": "model-00023-of-00031.safetensors",
|
| 715 |
+
"model.layers.61.self_attn.v_proj.weight": "model-00023-of-00031.safetensors",
|
| 716 |
+
"model.layers.62.input_layernorm.weight": "model-00024-of-00031.safetensors",
|
| 717 |
+
"model.layers.62.mlp.down_proj.weight": "model-00024-of-00031.safetensors",
|
| 718 |
+
"model.layers.62.mlp.gate_proj.weight": "model-00024-of-00031.safetensors",
|
| 719 |
+
"model.layers.62.mlp.up_proj.weight": "model-00024-of-00031.safetensors",
|
| 720 |
+
"model.layers.62.post_attention_layernorm.weight": "model-00024-of-00031.safetensors",
|
| 721 |
+
"model.layers.62.self_attn.k_proj.bias": "model-00024-of-00031.safetensors",
|
| 722 |
+
"model.layers.62.self_attn.k_proj.weight": "model-00024-of-00031.safetensors",
|
| 723 |
+
"model.layers.62.self_attn.o_proj.weight": "model-00024-of-00031.safetensors",
|
| 724 |
+
"model.layers.62.self_attn.q_proj.bias": "model-00024-of-00031.safetensors",
|
| 725 |
+
"model.layers.62.self_attn.q_proj.weight": "model-00024-of-00031.safetensors",
|
| 726 |
+
"model.layers.62.self_attn.v_proj.bias": "model-00024-of-00031.safetensors",
|
| 727 |
+
"model.layers.62.self_attn.v_proj.weight": "model-00024-of-00031.safetensors",
|
| 728 |
+
"model.layers.63.input_layernorm.weight": "model-00024-of-00031.safetensors",
|
| 729 |
+
"model.layers.63.mlp.down_proj.weight": "model-00024-of-00031.safetensors",
|
| 730 |
+
"model.layers.63.mlp.gate_proj.weight": "model-00024-of-00031.safetensors",
|
| 731 |
+
"model.layers.63.mlp.up_proj.weight": "model-00024-of-00031.safetensors",
|
| 732 |
+
"model.layers.63.post_attention_layernorm.weight": "model-00024-of-00031.safetensors",
|
| 733 |
+
"model.layers.63.self_attn.k_proj.bias": "model-00024-of-00031.safetensors",
|
| 734 |
+
"model.layers.63.self_attn.k_proj.weight": "model-00024-of-00031.safetensors",
|
| 735 |
+
"model.layers.63.self_attn.o_proj.weight": "model-00024-of-00031.safetensors",
|
| 736 |
+
"model.layers.63.self_attn.q_proj.bias": "model-00024-of-00031.safetensors",
|
| 737 |
+
"model.layers.63.self_attn.q_proj.weight": "model-00024-of-00031.safetensors",
|
| 738 |
+
"model.layers.63.self_attn.v_proj.bias": "model-00024-of-00031.safetensors",
|
| 739 |
+
"model.layers.63.self_attn.v_proj.weight": "model-00024-of-00031.safetensors",
|
| 740 |
+
"model.layers.64.input_layernorm.weight": "model-00025-of-00031.safetensors",
|
| 741 |
+
"model.layers.64.mlp.down_proj.weight": "model-00025-of-00031.safetensors",
|
| 742 |
+
"model.layers.64.mlp.gate_proj.weight": "model-00024-of-00031.safetensors",
|
| 743 |
+
"model.layers.64.mlp.up_proj.weight": "model-00025-of-00031.safetensors",
|
| 744 |
+
"model.layers.64.post_attention_layernorm.weight": "model-00025-of-00031.safetensors",
|
| 745 |
+
"model.layers.64.self_attn.k_proj.bias": "model-00024-of-00031.safetensors",
|
| 746 |
+
"model.layers.64.self_attn.k_proj.weight": "model-00024-of-00031.safetensors",
|
| 747 |
+
"model.layers.64.self_attn.o_proj.weight": "model-00024-of-00031.safetensors",
|
| 748 |
+
"model.layers.64.self_attn.q_proj.bias": "model-00024-of-00031.safetensors",
|
| 749 |
+
"model.layers.64.self_attn.q_proj.weight": "model-00024-of-00031.safetensors",
|
| 750 |
+
"model.layers.64.self_attn.v_proj.bias": "model-00024-of-00031.safetensors",
|
| 751 |
+
"model.layers.64.self_attn.v_proj.weight": "model-00024-of-00031.safetensors",
|
| 752 |
+
"model.layers.65.input_layernorm.weight": "model-00025-of-00031.safetensors",
|
| 753 |
+
"model.layers.65.mlp.down_proj.weight": "model-00025-of-00031.safetensors",
|
| 754 |
+
"model.layers.65.mlp.gate_proj.weight": "model-00025-of-00031.safetensors",
|
| 755 |
+
"model.layers.65.mlp.up_proj.weight": "model-00025-of-00031.safetensors",
|
| 756 |
+
"model.layers.65.post_attention_layernorm.weight": "model-00025-of-00031.safetensors",
|
| 757 |
+
"model.layers.65.self_attn.k_proj.bias": "model-00025-of-00031.safetensors",
|
| 758 |
+
"model.layers.65.self_attn.k_proj.weight": "model-00025-of-00031.safetensors",
|
| 759 |
+
"model.layers.65.self_attn.o_proj.weight": "model-00025-of-00031.safetensors",
|
| 760 |
+
"model.layers.65.self_attn.q_proj.bias": "model-00025-of-00031.safetensors",
|
| 761 |
+
"model.layers.65.self_attn.q_proj.weight": "model-00025-of-00031.safetensors",
|
| 762 |
+
"model.layers.65.self_attn.v_proj.bias": "model-00025-of-00031.safetensors",
|
| 763 |
+
"model.layers.65.self_attn.v_proj.weight": "model-00025-of-00031.safetensors",
|
| 764 |
+
"model.layers.66.input_layernorm.weight": "model-00025-of-00031.safetensors",
|
| 765 |
+
"model.layers.66.mlp.down_proj.weight": "model-00025-of-00031.safetensors",
|
| 766 |
+
"model.layers.66.mlp.gate_proj.weight": "model-00025-of-00031.safetensors",
|
| 767 |
+
"model.layers.66.mlp.up_proj.weight": "model-00025-of-00031.safetensors",
|
| 768 |
+
"model.layers.66.post_attention_layernorm.weight": "model-00025-of-00031.safetensors",
|
| 769 |
+
"model.layers.66.self_attn.k_proj.bias": "model-00025-of-00031.safetensors",
|
| 770 |
+
"model.layers.66.self_attn.k_proj.weight": "model-00025-of-00031.safetensors",
|
| 771 |
+
"model.layers.66.self_attn.o_proj.weight": "model-00025-of-00031.safetensors",
|
| 772 |
+
"model.layers.66.self_attn.q_proj.bias": "model-00025-of-00031.safetensors",
|
| 773 |
+
"model.layers.66.self_attn.q_proj.weight": "model-00025-of-00031.safetensors",
|
| 774 |
+
"model.layers.66.self_attn.v_proj.bias": "model-00025-of-00031.safetensors",
|
| 775 |
+
"model.layers.66.self_attn.v_proj.weight": "model-00025-of-00031.safetensors",
|
| 776 |
+
"model.layers.67.input_layernorm.weight": "model-00026-of-00031.safetensors",
|
| 777 |
+
"model.layers.67.mlp.down_proj.weight": "model-00026-of-00031.safetensors",
|
| 778 |
+
"model.layers.67.mlp.gate_proj.weight": "model-00026-of-00031.safetensors",
|
| 779 |
+
"model.layers.67.mlp.up_proj.weight": "model-00026-of-00031.safetensors",
|
| 780 |
+
"model.layers.67.post_attention_layernorm.weight": "model-00026-of-00031.safetensors",
|
| 781 |
+
"model.layers.67.self_attn.k_proj.bias": "model-00025-of-00031.safetensors",
|
| 782 |
+
"model.layers.67.self_attn.k_proj.weight": "model-00025-of-00031.safetensors",
|
| 783 |
+
"model.layers.67.self_attn.o_proj.weight": "model-00025-of-00031.safetensors",
|
| 784 |
+
"model.layers.67.self_attn.q_proj.bias": "model-00025-of-00031.safetensors",
|
| 785 |
+
"model.layers.67.self_attn.q_proj.weight": "model-00025-of-00031.safetensors",
|
| 786 |
+
"model.layers.67.self_attn.v_proj.bias": "model-00025-of-00031.safetensors",
|
| 787 |
+
"model.layers.67.self_attn.v_proj.weight": "model-00025-of-00031.safetensors",
|
| 788 |
+
"model.layers.68.input_layernorm.weight": "model-00026-of-00031.safetensors",
|
| 789 |
+
"model.layers.68.mlp.down_proj.weight": "model-00026-of-00031.safetensors",
|
| 790 |
+
"model.layers.68.mlp.gate_proj.weight": "model-00026-of-00031.safetensors",
|
| 791 |
+
"model.layers.68.mlp.up_proj.weight": "model-00026-of-00031.safetensors",
|
| 792 |
+
"model.layers.68.post_attention_layernorm.weight": "model-00026-of-00031.safetensors",
|
| 793 |
+
"model.layers.68.self_attn.k_proj.bias": "model-00026-of-00031.safetensors",
|
| 794 |
+
"model.layers.68.self_attn.k_proj.weight": "model-00026-of-00031.safetensors",
|
| 795 |
+
"model.layers.68.self_attn.o_proj.weight": "model-00026-of-00031.safetensors",
|
| 796 |
+
"model.layers.68.self_attn.q_proj.bias": "model-00026-of-00031.safetensors",
|
| 797 |
+
"model.layers.68.self_attn.q_proj.weight": "model-00026-of-00031.safetensors",
|
| 798 |
+
"model.layers.68.self_attn.v_proj.bias": "model-00026-of-00031.safetensors",
|
| 799 |
+
"model.layers.68.self_attn.v_proj.weight": "model-00026-of-00031.safetensors",
|
| 800 |
+
"model.layers.69.input_layernorm.weight": "model-00026-of-00031.safetensors",
|
| 801 |
+
"model.layers.69.mlp.down_proj.weight": "model-00026-of-00031.safetensors",
|
| 802 |
+
"model.layers.69.mlp.gate_proj.weight": "model-00026-of-00031.safetensors",
|
| 803 |
+
"model.layers.69.mlp.up_proj.weight": "model-00026-of-00031.safetensors",
|
| 804 |
+
"model.layers.69.post_attention_layernorm.weight": "model-00026-of-00031.safetensors",
|
| 805 |
+
"model.layers.69.self_attn.k_proj.bias": "model-00026-of-00031.safetensors",
|
| 806 |
+
"model.layers.69.self_attn.k_proj.weight": "model-00026-of-00031.safetensors",
|
| 807 |
+
"model.layers.69.self_attn.o_proj.weight": "model-00026-of-00031.safetensors",
|
| 808 |
+
"model.layers.69.self_attn.q_proj.bias": "model-00026-of-00031.safetensors",
|
| 809 |
+
"model.layers.69.self_attn.q_proj.weight": "model-00026-of-00031.safetensors",
|
| 810 |
+
"model.layers.69.self_attn.v_proj.bias": "model-00026-of-00031.safetensors",
|
| 811 |
+
"model.layers.69.self_attn.v_proj.weight": "model-00026-of-00031.safetensors",
|
| 812 |
+
"model.layers.7.input_layernorm.weight": "model-00004-of-00031.safetensors",
|
| 813 |
+
"model.layers.7.mlp.down_proj.weight": "model-00004-of-00031.safetensors",
|
| 814 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00031.safetensors",
|
| 815 |
+
"model.layers.7.mlp.up_proj.weight": "model-00004-of-00031.safetensors",
|
| 816 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00004-of-00031.safetensors",
|
| 817 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00004-of-00031.safetensors",
|
| 818 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00031.safetensors",
|
| 819 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00031.safetensors",
|
| 820 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00004-of-00031.safetensors",
|
| 821 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00004-of-00031.safetensors",
|
| 822 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00004-of-00031.safetensors",
|
| 823 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00004-of-00031.safetensors",
|
| 824 |
+
"model.layers.70.input_layernorm.weight": "model-00027-of-00031.safetensors",
|
| 825 |
+
"model.layers.70.mlp.down_proj.weight": "model-00027-of-00031.safetensors",
|
| 826 |
+
"model.layers.70.mlp.gate_proj.weight": "model-00027-of-00031.safetensors",
|
| 827 |
+
"model.layers.70.mlp.up_proj.weight": "model-00027-of-00031.safetensors",
|
| 828 |
+
"model.layers.70.post_attention_layernorm.weight": "model-00027-of-00031.safetensors",
|
| 829 |
+
"model.layers.70.self_attn.k_proj.bias": "model-00027-of-00031.safetensors",
|
| 830 |
+
"model.layers.70.self_attn.k_proj.weight": "model-00027-of-00031.safetensors",
|
| 831 |
+
"model.layers.70.self_attn.o_proj.weight": "model-00027-of-00031.safetensors",
|
| 832 |
+
"model.layers.70.self_attn.q_proj.bias": "model-00027-of-00031.safetensors",
|
| 833 |
+
"model.layers.70.self_attn.q_proj.weight": "model-00027-of-00031.safetensors",
|
| 834 |
+
"model.layers.70.self_attn.v_proj.bias": "model-00027-of-00031.safetensors",
|
| 835 |
+
"model.layers.70.self_attn.v_proj.weight": "model-00027-of-00031.safetensors",
|
| 836 |
+
"model.layers.71.input_layernorm.weight": "model-00027-of-00031.safetensors",
|
| 837 |
+
"model.layers.71.mlp.down_proj.weight": "model-00027-of-00031.safetensors",
|
| 838 |
+
"model.layers.71.mlp.gate_proj.weight": "model-00027-of-00031.safetensors",
|
| 839 |
+
"model.layers.71.mlp.up_proj.weight": "model-00027-of-00031.safetensors",
|
| 840 |
+
"model.layers.71.post_attention_layernorm.weight": "model-00027-of-00031.safetensors",
|
| 841 |
+
"model.layers.71.self_attn.k_proj.bias": "model-00027-of-00031.safetensors",
|
| 842 |
+
"model.layers.71.self_attn.k_proj.weight": "model-00027-of-00031.safetensors",
|
| 843 |
+
"model.layers.71.self_attn.o_proj.weight": "model-00027-of-00031.safetensors",
|
| 844 |
+
"model.layers.71.self_attn.q_proj.bias": "model-00027-of-00031.safetensors",
|
| 845 |
+
"model.layers.71.self_attn.q_proj.weight": "model-00027-of-00031.safetensors",
|
| 846 |
+
"model.layers.71.self_attn.v_proj.bias": "model-00027-of-00031.safetensors",
|
| 847 |
+
"model.layers.71.self_attn.v_proj.weight": "model-00027-of-00031.safetensors",
|
| 848 |
+
"model.layers.72.input_layernorm.weight": "model-00028-of-00031.safetensors",
|
| 849 |
+
"model.layers.72.mlp.down_proj.weight": "model-00028-of-00031.safetensors",
|
| 850 |
+
"model.layers.72.mlp.gate_proj.weight": "model-00027-of-00031.safetensors",
|
| 851 |
+
"model.layers.72.mlp.up_proj.weight": "model-00027-of-00031.safetensors",
|
| 852 |
+
"model.layers.72.post_attention_layernorm.weight": "model-00028-of-00031.safetensors",
|
| 853 |
+
"model.layers.72.self_attn.k_proj.bias": "model-00027-of-00031.safetensors",
|
| 854 |
+
"model.layers.72.self_attn.k_proj.weight": "model-00027-of-00031.safetensors",
|
| 855 |
+
"model.layers.72.self_attn.o_proj.weight": "model-00027-of-00031.safetensors",
|
| 856 |
+
"model.layers.72.self_attn.q_proj.bias": "model-00027-of-00031.safetensors",
|
| 857 |
+
"model.layers.72.self_attn.q_proj.weight": "model-00027-of-00031.safetensors",
|
| 858 |
+
"model.layers.72.self_attn.v_proj.bias": "model-00027-of-00031.safetensors",
|
| 859 |
+
"model.layers.72.self_attn.v_proj.weight": "model-00027-of-00031.safetensors",
|
| 860 |
+
"model.layers.73.input_layernorm.weight": "model-00028-of-00031.safetensors",
|
| 861 |
+
"model.layers.73.mlp.down_proj.weight": "model-00028-of-00031.safetensors",
|
| 862 |
+
"model.layers.73.mlp.gate_proj.weight": "model-00028-of-00031.safetensors",
|
| 863 |
+
"model.layers.73.mlp.up_proj.weight": "model-00028-of-00031.safetensors",
|
| 864 |
+
"model.layers.73.post_attention_layernorm.weight": "model-00028-of-00031.safetensors",
|
| 865 |
+
"model.layers.73.self_attn.k_proj.bias": "model-00028-of-00031.safetensors",
|
| 866 |
+
"model.layers.73.self_attn.k_proj.weight": "model-00028-of-00031.safetensors",
|
| 867 |
+
"model.layers.73.self_attn.o_proj.weight": "model-00028-of-00031.safetensors",
|
| 868 |
+
"model.layers.73.self_attn.q_proj.bias": "model-00028-of-00031.safetensors",
|
| 869 |
+
"model.layers.73.self_attn.q_proj.weight": "model-00028-of-00031.safetensors",
|
| 870 |
+
"model.layers.73.self_attn.v_proj.bias": "model-00028-of-00031.safetensors",
|
| 871 |
+
"model.layers.73.self_attn.v_proj.weight": "model-00028-of-00031.safetensors",
|
| 872 |
+
"model.layers.74.input_layernorm.weight": "model-00028-of-00031.safetensors",
|
| 873 |
+
"model.layers.74.mlp.down_proj.weight": "model-00028-of-00031.safetensors",
|
| 874 |
+
"model.layers.74.mlp.gate_proj.weight": "model-00028-of-00031.safetensors",
|
| 875 |
+
"model.layers.74.mlp.up_proj.weight": "model-00028-of-00031.safetensors",
|
| 876 |
+
"model.layers.74.post_attention_layernorm.weight": "model-00028-of-00031.safetensors",
|
| 877 |
+
"model.layers.74.self_attn.k_proj.bias": "model-00028-of-00031.safetensors",
|
| 878 |
+
"model.layers.74.self_attn.k_proj.weight": "model-00028-of-00031.safetensors",
|
| 879 |
+
"model.layers.74.self_attn.o_proj.weight": "model-00028-of-00031.safetensors",
|
| 880 |
+
"model.layers.74.self_attn.q_proj.bias": "model-00028-of-00031.safetensors",
|
| 881 |
+
"model.layers.74.self_attn.q_proj.weight": "model-00028-of-00031.safetensors",
|
| 882 |
+
"model.layers.74.self_attn.v_proj.bias": "model-00028-of-00031.safetensors",
|
| 883 |
+
"model.layers.74.self_attn.v_proj.weight": "model-00028-of-00031.safetensors",
|
| 884 |
+
"model.layers.75.input_layernorm.weight": "model-00029-of-00031.safetensors",
|
| 885 |
+
"model.layers.75.mlp.down_proj.weight": "model-00029-of-00031.safetensors",
|
| 886 |
+
"model.layers.75.mlp.gate_proj.weight": "model-00028-of-00031.safetensors",
|
| 887 |
+
"model.layers.75.mlp.up_proj.weight": "model-00029-of-00031.safetensors",
|
| 888 |
+
"model.layers.75.post_attention_layernorm.weight": "model-00029-of-00031.safetensors",
|
| 889 |
+
"model.layers.75.self_attn.k_proj.bias": "model-00028-of-00031.safetensors",
|
| 890 |
+
"model.layers.75.self_attn.k_proj.weight": "model-00028-of-00031.safetensors",
|
| 891 |
+
"model.layers.75.self_attn.o_proj.weight": "model-00028-of-00031.safetensors",
|
| 892 |
+
"model.layers.75.self_attn.q_proj.bias": "model-00028-of-00031.safetensors",
|
| 893 |
+
"model.layers.75.self_attn.q_proj.weight": "model-00028-of-00031.safetensors",
|
| 894 |
+
"model.layers.75.self_attn.v_proj.bias": "model-00028-of-00031.safetensors",
|
| 895 |
+
"model.layers.75.self_attn.v_proj.weight": "model-00028-of-00031.safetensors",
|
| 896 |
+
"model.layers.76.input_layernorm.weight": "model-00029-of-00031.safetensors",
|
| 897 |
+
"model.layers.76.mlp.down_proj.weight": "model-00029-of-00031.safetensors",
|
| 898 |
+
"model.layers.76.mlp.gate_proj.weight": "model-00029-of-00031.safetensors",
|
| 899 |
+
"model.layers.76.mlp.up_proj.weight": "model-00029-of-00031.safetensors",
|
| 900 |
+
"model.layers.76.post_attention_layernorm.weight": "model-00029-of-00031.safetensors",
|
| 901 |
+
"model.layers.76.self_attn.k_proj.bias": "model-00029-of-00031.safetensors",
|
| 902 |
+
"model.layers.76.self_attn.k_proj.weight": "model-00029-of-00031.safetensors",
|
| 903 |
+
"model.layers.76.self_attn.o_proj.weight": "model-00029-of-00031.safetensors",
|
| 904 |
+
"model.layers.76.self_attn.q_proj.bias": "model-00029-of-00031.safetensors",
|
| 905 |
+
"model.layers.76.self_attn.q_proj.weight": "model-00029-of-00031.safetensors",
|
| 906 |
+
"model.layers.76.self_attn.v_proj.bias": "model-00029-of-00031.safetensors",
|
| 907 |
+
"model.layers.76.self_attn.v_proj.weight": "model-00029-of-00031.safetensors",
|
| 908 |
+
"model.layers.77.input_layernorm.weight": "model-00029-of-00031.safetensors",
|
| 909 |
+
"model.layers.77.mlp.down_proj.weight": "model-00029-of-00031.safetensors",
|
| 910 |
+
"model.layers.77.mlp.gate_proj.weight": "model-00029-of-00031.safetensors",
|
| 911 |
+
"model.layers.77.mlp.up_proj.weight": "model-00029-of-00031.safetensors",
|
| 912 |
+
"model.layers.77.post_attention_layernorm.weight": "model-00029-of-00031.safetensors",
|
| 913 |
+
"model.layers.77.self_attn.k_proj.bias": "model-00029-of-00031.safetensors",
|
| 914 |
+
"model.layers.77.self_attn.k_proj.weight": "model-00029-of-00031.safetensors",
|
| 915 |
+
"model.layers.77.self_attn.o_proj.weight": "model-00029-of-00031.safetensors",
|
| 916 |
+
"model.layers.77.self_attn.q_proj.bias": "model-00029-of-00031.safetensors",
|
| 917 |
+
"model.layers.77.self_attn.q_proj.weight": "model-00029-of-00031.safetensors",
|
| 918 |
+
"model.layers.77.self_attn.v_proj.bias": "model-00029-of-00031.safetensors",
|
| 919 |
+
"model.layers.77.self_attn.v_proj.weight": "model-00029-of-00031.safetensors",
|
| 920 |
+
"model.layers.78.input_layernorm.weight": "model-00030-of-00031.safetensors",
|
| 921 |
+
"model.layers.78.mlp.down_proj.weight": "model-00030-of-00031.safetensors",
|
| 922 |
+
"model.layers.78.mlp.gate_proj.weight": "model-00030-of-00031.safetensors",
|
| 923 |
+
"model.layers.78.mlp.up_proj.weight": "model-00030-of-00031.safetensors",
|
| 924 |
+
"model.layers.78.post_attention_layernorm.weight": "model-00030-of-00031.safetensors",
|
| 925 |
+
"model.layers.78.self_attn.k_proj.bias": "model-00029-of-00031.safetensors",
|
| 926 |
+
"model.layers.78.self_attn.k_proj.weight": "model-00029-of-00031.safetensors",
|
| 927 |
+
"model.layers.78.self_attn.o_proj.weight": "model-00029-of-00031.safetensors",
|
| 928 |
+
"model.layers.78.self_attn.q_proj.bias": "model-00029-of-00031.safetensors",
|
| 929 |
+
"model.layers.78.self_attn.q_proj.weight": "model-00029-of-00031.safetensors",
|
| 930 |
+
"model.layers.78.self_attn.v_proj.bias": "model-00029-of-00031.safetensors",
|
| 931 |
+
"model.layers.78.self_attn.v_proj.weight": "model-00029-of-00031.safetensors",
|
| 932 |
+
"model.layers.79.input_layernorm.weight": "model-00030-of-00031.safetensors",
|
| 933 |
+
"model.layers.79.mlp.down_proj.weight": "model-00030-of-00031.safetensors",
|
| 934 |
+
"model.layers.79.mlp.gate_proj.weight": "model-00030-of-00031.safetensors",
|
| 935 |
+
"model.layers.79.mlp.up_proj.weight": "model-00030-of-00031.safetensors",
|
| 936 |
+
"model.layers.79.post_attention_layernorm.weight": "model-00030-of-00031.safetensors",
|
| 937 |
+
"model.layers.79.self_attn.k_proj.bias": "model-00030-of-00031.safetensors",
|
| 938 |
+
"model.layers.79.self_attn.k_proj.weight": "model-00030-of-00031.safetensors",
|
| 939 |
+
"model.layers.79.self_attn.o_proj.weight": "model-00030-of-00031.safetensors",
|
| 940 |
+
"model.layers.79.self_attn.q_proj.bias": "model-00030-of-00031.safetensors",
|
| 941 |
+
"model.layers.79.self_attn.q_proj.weight": "model-00030-of-00031.safetensors",
|
| 942 |
+
"model.layers.79.self_attn.v_proj.bias": "model-00030-of-00031.safetensors",
|
| 943 |
+
"model.layers.79.self_attn.v_proj.weight": "model-00030-of-00031.safetensors",
|
| 944 |
+
"model.layers.8.input_layernorm.weight": "model-00004-of-00031.safetensors",
|
| 945 |
+
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00031.safetensors",
|
| 946 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00004-of-00031.safetensors",
|
| 947 |
+
"model.layers.8.mlp.up_proj.weight": "model-00004-of-00031.safetensors",
|
| 948 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00031.safetensors",
|
| 949 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00004-of-00031.safetensors",
|
| 950 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00031.safetensors",
|
| 951 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00031.safetensors",
|
| 952 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00004-of-00031.safetensors",
|
| 953 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00004-of-00031.safetensors",
|
| 954 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00004-of-00031.safetensors",
|
| 955 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00031.safetensors",
|
| 956 |
+
"model.layers.9.input_layernorm.weight": "model-00005-of-00031.safetensors",
|
| 957 |
+
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00031.safetensors",
|
| 958 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00004-of-00031.safetensors",
|
| 959 |
+
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00031.safetensors",
|
| 960 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00031.safetensors",
|
| 961 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00004-of-00031.safetensors",
|
| 962 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00031.safetensors",
|
| 963 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00031.safetensors",
|
| 964 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00004-of-00031.safetensors",
|
| 965 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00031.safetensors",
|
| 966 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00004-of-00031.safetensors",
|
| 967 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00031.safetensors",
|
| 968 |
+
"model.norm.weight": "model-00030-of-00031.safetensors"
|
| 969 |
+
}
|
| 970 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"extra_special_tokens": {},
|
| 203 |
+
"model_max_length": 131072,
|
| 204 |
+
"pad_token": "<|endoftext|>",
|
| 205 |
+
"split_special_tokens": false,
|
| 206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
+
"unk_token": null
|
| 208 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|